Reading Disability (RD) is the most common learning disability, affecting 10 – 15% of school age children. It incurs major functional impairments at all stages of life, with a wealth of data documenting lifelong disadvantages in educational and occupational attainment. Therefore, identifying effective and affordable treatments for RD is a high priority for reading researchers and educators. Problematically, current evidence-based reading interventions largely rely on services by trained specialists, often in clinical settings. As such, many schools are unable to provide reading interventions for their students. A second, equally problematic issue, is that not all children with RD benefit equally from treatment, with a substantial portion of children classified as “non-responders”. This line of research suggests that children with comorbidities and other baseline cognitive states or conditions may be more likely to be non-responders, however these factors remain underexplored. To begin to address these problems, this project will evaluate the effectiveness of a technology-based reading intervention (GraphoLearn) that can be delivered in the home, in a large and well characterized sample of RD children. This work leverages the availability of the Healthy Brain Network (HBN), an ongoing study of mental health and learning disorders in children, ages 5.0-21.0, whose family have concerns about behavior and/or learning (target n = 10,000; current enrollment = 3000+). To this end, we will implement a large-scale, randomized controlled trial (RCT) of home-administered GraphoLearn, in 450 RD children (boys and girls, ages 6.0-10.0) to determine its effectiveness and identify factors that facilitate or hinder intervention gains. The HBN sample is optimal for exploring an extensive set of factors that may affect treatment outcomes (e.g., compliance, cognitive, emotional, neurobiological). In this project, machine learning approaches (Random Forest Regression models) will be used identify factors that predict GraphoLearn outcomes, based on an a priori set of baseline cognitive, behavioral, psychiatric, and brain variables. Further, exploratory analyses will compare responders versus non-responders to identify pre-intervention MRI- and EEG-based biotypes associated with response.